Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already carry destructiveHint=true and idempotentHint=true, but the description adds real value beyond them: attachments return to the underlagspool (underlagspoolen), the required 'reconcile' permission, and a caution to act only on user instruction. This is meaningful behavioral context for a destructive operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, with the action and the delete semantics front-loaded. The final 'Argument: orgnr, draft_id' clause is redundant filler already conveyed by the schema, a minor blemish.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive mutation with annotations covering safety, the description supplies the missing pieces an agent needs: the permission requirement, the side effect on attachments, and the user-consent condition. No output schema is required for a delete operation, so it is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: orgnr is well documented in the schema with format and a list_companies pointer, while draft_id has no description anywhere. The description's trailing 'Argument: orgnr, draft_id' merely restates the names and adds no format or meaning, so it does not compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: reject (delete) a pending voucher draft. It is cleanly distinguishable from siblings like approve_voucher_draft and edit_voucher_draft, and the parenthetical 'ta bort' confirms the delete semantics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to perform this only when the user has instructed a rejection, which is clear when-to-use guidance. It does not name the natural alternative (approve_voucher_draft) as the contrasting action, so a 4 rather than 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.